Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 8-RES-MATRYOSHKA-DC
    4. 31181
    Prev
    Next
    INDEX
    Explanations

    text related to political geography, especially anything involving the former Soviet Union and related countries

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    extAlignment
    -0.82
    
    -0.82
    Personendaten
    -0.81
    DockStyle
    -0.76
     propOrder
    -0.73
     AssemblyCulture
    -0.71
    MessageTagHelper
    -0.70
     pinulongan
    -0.68
    ImageContext
    -0.67
     NSCoder
    -0.66
    POSITIVE LOGITS
     rapidly
    0.43
     mix
    0.42
    gorov
    0.42
     slowly
    0.41
    لمات
    0.41
    YI
    0.41
    fromLTRB
    0.41
      
    0.41
     đạt
    0.41
     yii
    0.40
    Activations Density 0.108%

    No Known Activations